Raad, LaraOliver Parera, MariaBallester, ColomaHaro Ortega, GloriaMeinhardt Llopis, Enric2020-09-022020-09-022020Raad L, Oliver M, Ballester C, Haro G, Meinhardt E. On anisotropic optical flow inpainting algorithms. Image Processing On Line Journal. 2020;10:78-104. DOI: 10.5201/ipol.2020.2812105–1232http://hdl.handle.net/10230/45244This work describes two anisotropic optical flow inpainting algorithms. The first one recovers the missing flow values using the Absolutely Minimizing Lipschitz Extension partial differential equation (also called infinity Laplacian equation) and the second one uses the Laplace partial differential equation, both defined on a Riemmanian manifold. The Riemannian manifold is defined by endowing the plane domain with an appropriate metric depending on the reference video frame. A detailed analysis of both approaches is provided and their results are compared on three different applications: flow densification, occlusion inpainting and large hole inpainting.application/pdfeng© 2020 IPOL & the authors. The article is distributed under a Creative Commons CC-BY-NC-SA license.On anisotropic optical flow inpainting algorithmsinfo:eu-repo/semantics/articlehttps://doi.org/10.5201/ipol.2020.281Optical flow inpaintingAbsolutely minimizing Lipschitz extensionLaplace-Beltramiinfo:eu-repo/semantics/openAccess